No abstract

Gas-jet supercharger is the core equipment of underground gas storage, whose working performance directly affects the working state of gas storage. Therefore, Relief-F algorithm was used to select the key features to determine the key factors causing the failure of the supercharger. Collecting the main state categories and related characteristic parameters of the supercharger, and calculating the feature scores for the normalized sample set by Relief-F algorithm. At the same time, ranking the feature scores and removing the feature whose importance score is less than the threshold value. Eleven key features, such as engine exhaust temperature I and engine exhaust temperature bar, were obtained, which provide a basis for the fault identification of supercharger.